The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

As ChatGPT goes viral, generative AI (AIGC, aka AI-generated content) has made headlines
everywhere because of its ability to analyze and create text, images, and beyond. With such …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

Abstract Language models have been successfully used to model natural signals, such as
images, speech, and music. A key component of these models is a high quality neural …

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called Vall-E) using discrete codes derived from …

Abstract 3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal
undertaking in autonomous driving aiming to predict the voxel occupancy within volumetric …

We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained
with minimal supervision. By combining two types of discrete speech representations, we …

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …

While recent large-scale text-to-speech (TTS) models have achieved significant progress,
they still fall short in speech quality, similarity, and prosody. Considering speech intricately …

Conventional methods for human motion synthesis have either been deterministic or have
had to struggle with the trade-off between motion diversity vs motion quality. In response to …